数据驱动下基于旅客需求的高铁差异化定价优化研究

A Study on the Optimization of Data-driven High-speed Railway Differentiated Pricing Based on Passengers’Demand

为提高旅客服务质量,提升铁路运输企业收益,多条高铁线路实行了市场化票价机制。基于此,通过集成的机器学习(EML)算法深入分析旅客需求数据,预测旅客对价格和旅行时间的敏感度和需求变化,并将这些变化应用于动态定价策略中,形成一种集合了三种算法的ESA(EML-SA-ALNS)算法。京沪高铁的实际数据验证了模型的效果,结果显示模型能有效平衡旅客需求与铁路运输企业的收益。

In order to improve the passenger service and increase the revenue of railway transport enterprises,a number of high-speed railway lines have implemented a market-based fares mechanism.Based on this,the ensemble machine learning(EML)algorithm is used to make deep analysis on the data on passengers’demand to accurately predict passengers’sensitivity to fares and travel time and the changes in their demand,and these changes are applied to the high-speed railway dynamic pricing strategy to form an ESA(EML-SA-ALNS)algorithm that aggregates three algorithms.The effect of the model is verified by the actual data from the Beijing—Shanghai high-speed railway,and the results show that this model can effectively balance passengers’demand and the revenue of railway transportation enterprises,providing innovative methods and ideas for the dynamic optimization of high-speed railway fares strategy.